Intelligent graphical feature generation for user content

Abstract

A mobile application includes a user interface for creating video or hypervideo content comprising a plurality of visual cards. User text input is received for display on one of the visual cards, and text analysis information comprising a tone of the text and a topic of the text and/or one or more keywords of the text is identified based on the text input. Using the text analysis information, one or more media assets are retrieved and a theme for the visual card is selected. The visual card is then constructed based on the text, the media assets, and a style definition associated with the theme. Additional visual cards can be created in a similar manner, resulting in a complete presentation.

What is claimed is: 
     
         1 . A computer-implemented method for media content generation, the method comprising:
 providing an application having a user interface for creating a video on a mobile device, the video comprising a plurality of visual cards;   receiving an input of text from a user of the application for display on one of the visual cards;   retrieving one or more media assets from an online searchable media service;   selecting a theme or template for the visual card; and   constructing the visual card based on the text, the one or more media assets, and a style definition associated with the theme or template.   
     
     
         2 . The method of  claim 1 , further comprising identifying, based on the text, text analysis information comprising (i) a tone of the text and (ii) at least one of a topic of the text and one or more keywords of the text. 
     
     
         3 . The method of  claim 2 , wherein the one or more media assets are retrieved based on at least a portion of the text analysis information. 
     
     
         4 . The method of  claim 2 , further comprising selecting the template or theme for the visual card based on at least a portion of the text analysis information. 
     
     
         5 . The method of  claim 2 , wherein identifying the text analysis information comprises providing the text as input to a language recognition service and receiving as output from the language recognition service the text analysis information. 
     
     
         6 . The method of  claim 2 , wherein retrieving the media assets comprises providing at least a portion of the text analysis information as input to an online searchable media service and receiving as output from the online searchable media service the one or more media assets. 
     
     
         7 . The method of  claim 2 , wherein selecting the theme or template comprises:
 identifying whether the tone comprises a positive sentiment, a negative sentiment, or a neutral sentiment; and   selecting a theme having elements corresponding to the identified sentiment.   
     
     
         8 . The method of  claim 1 , wherein constructing the visual card comprises positioning the one or more media assets on the visual card in a universal coordinate space. 
     
     
         9 . The method of  claim 1 , wherein constructing the visual card based on the style definition comprises applying to the visual card a plurality of visual composition elements identified by the style definition, the visual composition elements including at least one of a background image, a background pattern, a background color, a border, a gradient, a layout, an object transform, a font type, a font size, and a font color. 
     
     
         10 . The method of  claim 1 , wherein the style definition defines a set of aesthetically compatible visual composition elements. 
     
     
         11 . The method of  claim 10 , further comprising storing the visual composition elements in a file folder structure comprising a plurality of folders each containing a style definition file associated with a particular theme and a plurality of elements compatible with the particular theme. 
     
     
         12 . The method of  claim 1 , further comprising:
 detecting a gesture made by the user on the mobile device;   in response to the gesture, selecting a new template or theme of the visual card and updating a composition of the visual card based on the new template or theme.   
     
     
         13 . The method of  claim 12 , wherein the gesture comprises a swipe on a touch-enabled display screen of the mobile device. 
     
     
         14 . The method of  claim 1 , further comprising automatically determining a duration of the visual card within the video and configuring the video to display the visual card for the determined duration. 
     
     
         15 . The method of  claim 14 , wherein automatically determining the duration of the visual card comprises calculating the duration based on at least one of a number of characters of text on the visual card, a number of words on the visual card, a number of images on the visual card, and a length of a video or animation on the visual card. 
     
     
         16 . The method of  claim 1 , wherein the video comprises a hypervideo. 
     
     
         17 . The method of  claim 16 , further comprising exporting the hypervideo to a text file. 
     
     
         18 . The method of  claim 17 , further comprising sharing the text file with one or more other users. 
     
     
         19 . The method of  claim 17 , further comprising regenerating the hypervideo from the text file. 
     
     
         20 . The method of  claim 1 , wherein the plurality of visual cards comprises an introduction card, a conclusion card, and at least one intermediate card. 
     
     
         21 . The method of  claim 21 , further comprising, during a presentation of the video to the user on the mobile device, automatically adapting a display of the visual card based on an aspect ratio of a display screen of the mobile device. 
     
     
         22 . A system for media content generation creation, the system comprising:
 at least one memory for storing computer-executable instructions; and   at least one processor for executing the instructions stored on the at least one memory, wherein execution of the instructions programs the at least one processor to perform operations comprising:
 providing an application having a user interface for creating a video on a mobile device, the video comprising a plurality of visual cards; 
 receiving an input of text from a user of the application for display on one of the visual cards; 
 retrieving one or more media assets from an online searchable media service; 
 selecting a theme or template for the visual card; and 
 constructing the visual card based on the text, the one or more media assets, and a style definition associated with the theme or template. 
   
     
     
         23 . The system of  claim 22 , wherein the operations further comprise identifying, based on the text, text analysis information comprising (i) a tone of the text and (ii) at least one of a topic of the text and one or more keywords of the text. 
     
     
         24 . The system of  claim 23 , wherein the one or more media assets are retrieved based on at least a portion of the text analysis information. 
     
     
         25 . The system of  claim 23 , wherein the operations further comprise selecting the template or theme for the visual card based on at least a portion of the text analysis information. 
     
     
         26 . The system of  claim 23 , wherein identifying the text analysis information comprises providing the text as input to a language recognition service and receiving as output from the language recognition service the text analysis information. 
     
     
         27 . The system of  claim 23 , wherein retrieving the media assets comprises providing at least a portion of the text analysis information as input to an online searchable media service and receiving as output from the online searchable media service the one or more media assets. 
     
     
         28 . The system of  claim 23 , wherein selecting the theme or template comprises:
 identifying whether the tone comprises a positive sentiment, a negative sentiment, or a neutral sentiment; and   selecting a theme having elements corresponding to the identified sentiment.   
     
     
         29 . The system of  claim 22 , wherein constructing the visual card based on the style definition comprises applying to the visual card a plurality of visual composition elements identified by the style definition, the visual composition elements including at least one of a background image, a background pattern, a background color, a border, a gradient, a layout, an object transform, a font type, a font size, and a font color. 
     
     
         30 . The system of  claim 22 , wherein the operations further comprise:
 detecting a gesture made by the user on the mobile device;   in response to the gesture, selecting a new template or theme of the visual card and updating a composition of the visual card based on the new template or theme.